Carlos Greg Diuk-Wasser, Ph.D.

Research Scientist
Computational Social Science - Central Social Impact team
Meta, Inc.

carlosdiuk gmail com

Some of the work I do at Facebook takes the form of blog posts:

• Don't be seduced by the allure: A guide for how (not) to use proxy metrics in experiments

• Three and a half degrees of separation: How connected is the Facebook graph?

• World Cup Fan Migration: How fan support migrates from team to team during World Cup 2014.

• The Formation of Love: How couples interact before and after the relationship is formed. (also here)

• Cupid in your Network: The network properties of Facebook matchmakers.

Other:

• TEDxRioDeLaPlata talk (with English subtitles).

• Video of my Ignite San Francisco 2014 talk: A quantitative philology of introspection.

Also check my Google Scholar profile.

Peer-reviewed Publications:

2021. “Social Catalysts: Characterizing People Who Spark Conversations Among Others”, Martin Saveski, Farshad Kooti, Sylvia Morelli Vitousek, Carlos Diuk, Bryce Bartlett, Lada A Adamic. Proceedings of the ACM on Human-Computer Interaction. CSCW 2021. pdf

2014. “Optimal Behavioral Hierarchy”, Alec Solway, Carlos Diuk, Natalia Córdova, Debbie Yee, Andrew G. Barto, Yael Niv, Matthew M. Botvinick. PLOS Computational Biology. link

2014. “Parsing heuristic and forward search in first-graders game-play behavior”, Luciano Paz, Andrea Goldin, Carlos Diuk and Mariano Sigman. Cognitive Science. link

2013. “Divide and conquer: hierarchical reinforcement learning and task decomposition in humans.”, Carlos Diuk, Anna Schapiro, Natalia Córdova, José Ribas-Fernandes, Yael Niv and Matthew M. Botvinick. In Computational and Robotic Models of the Hierarchical Organization of Behavior. Edited by Baldassare G and Mirolli M. Springer Verlag.link

2013. “Hierarchical Learning Induces Two Simultaneous, But Separable, Prediction Errors in Human Basal Ganglia”, Carlos Diuk, Karin Tsai, Jonathan Wallis, Matthew M. Botvinick and Yael Niv. The Journal of Neuroscience. link

2012. “A quantitative philology of introspection”, Carlos Diuk, Diego F. Slezak, Iván Raskovsky, Mariano Sigman and Guillermo Cecchi. Frontiers in Integrative Neuroscience. link

2011. “A Neural Signature of Hierarchical Reinforcement Learning”, José J.F. Ribas-Fernandes, Alec Solway, Carlos Diuk, Joseph T. McGuire, Andrew G. Barto, Yael Niv and Matthew M. Botvinick. Neuron, Volume 71, Issue 2, 370-379. abstract

2010. PhD Thesis: "An object-oriented representation for efficient reinforcement learning". pdf

2010. “Generalizing Apprenticeship Learning across Hypothesis Classes”, Thomas J. Walsh, Kaushik Subramanian, Michael L. Littman and Carlos Diuk. ICML 2010. pdf

2009. “The Adaptive k-Meteorologists Problem and Its Application to Structure Learning and Feature Selection in Reinforcement Learning”, Carlos Diuk, Lihong Li and Bethany Leffler. ICML 2009. pdf / videolecture

2009. “Exploring Compact Reinforcement-Learning Representations with Linear Regression”, Thomas J. Walsh, István Szita, Carlos Diuk, and Michael L. Littman. UAI 2009. pdf

2008. “An Object-Oriented Representation for Efficient Reinforcement Learning”, Carlos Diuk, Andre Cohen and Michael L. Littman. ICML 2008. pdf / videolecture

2008. “Hierarchical Reinforcement Learning”, Carlos Diuk and Michael Littman. Encyclopedia of Artificial Intelligence, IGI Global, July 2008.

2007. “Efficient Structure Learning in Factored-state MDPs”, Alexander L. Strehl, Carlos Diuk and Michael L. Littman. AAAI 2007.pdf

2007. “An adaptive anomaly detector for worm detection ”, John Mark Agosta, Carlos Diuk, Jaideep Chandrashekar and Carl Livadas. Second Workshop on Tackling Computer Systems Problems with Machine Learning Techniques (sysML-07). pdf

2006. “A Hierarchical Approach to Efficient Reinforcement Learning in Deterministic Domains”, Carlos Diuk, Alexander L. Strehl and Michael L. Littman. AAMAS’06. pdf

2003. “Una herramienta computacional para la reconstrucción de genealogías históricas.”, Carlos Diuk. Licenciatura Dissertation. Dept. of Computer Science, Universidad de Buenos Aires. pdf

2002. “Computer tools for reconstructing a genealogy”, Carlos Diuk and Enrique Tándeter. International Journal of History and Computing. Edinburgh University Press. pdf

Other publications and talks:

2013. “Compositional policy priors”, Wingate, David; Diuk, Carlos; O'Donnell, Timothy; Tenenbaum, Joshua; Gershman, Samuel. Technical Report 2013-007. MIT CSAIL. link

2010. “Hierarchical Reinforcement Learning: An fMRI Study of learning in a two-level gambling task ”, Carlos Diuk, Matthew Botvinick, Andrew Barto and Yael Niv. Society for Neuroscience Meeting 2010 (SfN 2010). pdf

2010. “The emergence of the modern concept of introspection: a quantitative linguistic analysis”, Ivan Raskovsky, Diego Fernández Slezak, Carlos Diuk and Guillermo Cecchi. NAACL Young Investigators Workshop 2010. pdf

2006. Invited Speaker at AAMAS Hierarchical Autonomous Agents and Multi-Agent Systems: “A Hierarchical Approach to Efficient Reinforcement Learning”.

2006. “Using Classifiers to Transfer Knowledge ”, Thomas J. Walsh, Carlos Diuk and Michael Littman. Presented at the New York Academy of Science Machine Learning Symposium.

2006. “Efficient exploration and learning of structure in factored-state MDPs ”, Carlos Diuk, Michael L. Littman, Alexander L. Strehl. Presented at NIPS Workshop “Towards a New Reinforcement Learning?”.

2005. “A Hierarchical Approach to Efficient Reinforcement Learning in Factored State Spaces”, Carlos Diuk, Michael L. Littman, and Alexander L. Strehl. Presented at the the 22nd International Conference on Machine Learning (ICML 2005), Workshop on Rich Representations for Reinforcement Learning, Bonn, Germany, 2005.